Reflection-aware Generative Novel View Synthesis

• URL: http://arxiv.org/abs/2609.05382v1
• Date: Fri, 04 Sep 2026 17:33:45 GMT
• Title: Reflection-aware Generative Novel View Synthesis
• Abstract summary: Ref-GeNVS is a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes.<n>On synthetic and real scenes including mirrors, Ref-GeNVS outperforms recent generative NVS methods.
• Score: 29.38808167444839
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose Ref-GeNVS, a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes. Existing multi-view diffusion models often fail to recognize the mirror in the scene and cannot exploit reflected content for scene generation. To fix this issue without additional training, our key idea is to treat a mirror image as two complementary views. From input images, we estimate the mirror plane and reflect camera poses to form virtual views. Based on this virtual view setup, we propose a two-stage generation method consisting of Mirror-gated attention and Reflection injection, which enables reflection-consistent NVS by explicitly leveraging reflection relationships in a multi-view diffusion model. Ref-GeNVS inherits the strong generalizability of the multi-view diffusion backbone, while it does not require finetuning. On synthetic and real scenes including mirrors, Ref-GeNVS outperforms recent generative NVS methods by generating reflection-consistent and contextually coherent novel views, revealing scene structure visible only through mirrors. Project page: https://kim-geonu.github.io/Ref-GeNVS/

Related papers

• MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation [46.878264012748694]
  We propose a reflection-aware video inpainting framework that models scene-to-mirror relationships during generation.<n>MirrorWorld achieves improved reflection reconstruction quality over representative image-based reflection generation methods.
  arXiv  Detail & Related papers  (2026-08-07T17:58:10Z)
• Reflection Generation for Composite Image Using Diffusion Model [22.699034413532285]
  Shadow generation has been extensively studied, but reflection generation remains largely underexplored.<n>We inject the prior information of reflection placement and reflection appearance into foundation diffusion model.<n>To support training, we construct the first large-scale object reflection dataset DEROBA.
  arXiv  Detail & Related papers  (2026-04-02T15:35:28Z)
• Seeing Through Reflections: Advancing 3D Scene Reconstruction in Mirror-Containing Environments with Gaussian Splatting [3.0501972844045273]
  We present MirrorScene3D, a dataset featuring diverse indoor scenes, 1256 high-quality images, and annotated mirror masks.<n>We propose ReflectiveGS, an extension of 3D Gaussian Splatting that utilizes mirror reflections as complementary viewpoints.<n>Experiments on MirrorScene3D show that ReflectiveGaussian outperforms existing methods in SSIM, PSNR, LPIPS, and training speed.
  arXiv  Detail & Related papers  (2025-09-23T13:06:00Z)
• NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives [7.116175288307167]
  We present NeRF-MD, a method which shows that NeRFs can be considered as mirror detectors.<n>We first compute an initial estimate of the scene geometry by training a standard NeRF.<n>We then jointly optimize the radiance field and mirror geometry in a second training stage to refine their quality.
  arXiv  Detail & Related papers  (2025-01-07T18:59:53Z)
• MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds [56.77548728485841]
  We propose a fast single-stage feed-forward network MV-DUSt3R to handle more views, reduce errors, and improve inference time.<n>At its core are multi-view decoder blocks which exchange information across any number of views while considering one reference view.<n>To make our method robust to reference view selection, we further propose MV-DUSt3R+, which employs cross-reference-view blocks to fuse information across different reference view choices.
  arXiv  Detail & Related papers  (2024-12-09T20:34:55Z)
• Monocular Identity-Conditioned Facial Reflectance Reconstruction [71.90507628715388]
  Existing methods rely on a large amount of light-stage captured data to learn facial reflectance models. We learn the reflectance prior in image space rather than UV space and present a framework named ID2Reflectance. Our framework can directly estimate the reflectance maps of a single image while using limited reflectance data for training.
  arXiv  Detail & Related papers  (2024-03-30T09:43:40Z)
• Revisiting Single Image Reflection Removal In the Wild [83.42368937164473]
  This research focuses on the issue of single-image reflection removal (SIRR) in real-world conditions. We devise an advanced reflection collection pipeline that is highly adaptable to a wide range of real-world reflection scenarios. We develop a large-scale, high-quality reflection dataset named Reflection Removal in the Wild (RRW)
  arXiv  Detail & Related papers  (2023-11-29T02:31:10Z)
• Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracing [33.852910220413655]
  We present a novel neural rendering framework, named Mirror-NeRF, which is able to learn accurate geometry and reflection of the mirror. Mirror-NeRF supports various scene manipulation applications with mirrors, such as adding new objects or mirrors into the scene and synthesizing the reflections of these new objects in mirrors.
  arXiv  Detail & Related papers  (2023-08-07T03:48:07Z)
• Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance [78.34235841168031]
  We present a novel two-stage network with reflection-aware guidance (RAGNet) for single image reflection removal (SIRR) RAG can be used (i) to mitigate the effect of reflection from the observation, and (ii) to generate mask in partial convolution for mitigating the effect of deviating from linear combination hypothesis. Experiments on five commonly used datasets demonstrate the quantitative and qualitative superiority of our RAGNet in comparison to the state-of-the-art SIRR methods.
  arXiv  Detail & Related papers  (2020-12-02T03:14:57Z)
• Polarized Reflection Removal with Perfect Alignment in the Wild [66.48211204364142]
  We present a novel formulation to removing reflection from polarized images in the wild. We first identify the misalignment issues of existing reflection removal datasets. We build a new dataset with more than 100 types of glass in which obtained transmission images are perfectly aligned with input mixed images.
  arXiv  Detail & Related papers  (2020-03-28T13:29:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.